second_constantine/
magistral-small:24b

61 2 days ago

Building upon Mistral Small 3.2 (2506), with added reasoning capabilities, undergoing SFT from Magistral Medium traces and RL on top, it's a small, efficient reasoning model with 24B parameters.(quantized UD-Q5_K_XL)

vision tools thinking 24b
... /
params
3f9ab15e228b · 86B
{
"min_p": 0,
"repeat_penalty": 1,
"stop": [
"</s>"
],
"temperature": 0.15,
"top_p": 1
}